Comments (4)
hako-mikan
commented on August 20, 2024
3
Thanks reporting. Added code to release memory. It improved in my environment, please try it.
from sd-webui-lora-block-weight.
Manaball123
commented on August 20, 2024
Try adding a line under process(): (around line 200)
torch.cuda.empty_cache()
Note that I haven't extensively tested this, and this may lower your overall performance.
I am speculating that this is caused by the new LoRA being allocated(one with modified weights) not properly being freed after allocation.
from sd-webui-lora-block-weight.
Daniel-Poke
commented on August 20, 2024
Okay, I'm not crazy, I thought this extension just used a high amount of memory so I turn it off when I am bulk generating, but those usage graphs show a definite climb in memory.
Thank you for reporting and thanks @hako-mikan for resolving (potentially). I will test this out also.
EDIT: Been generating like normal and doing some high res fix perfectly fine, this seems to have resolved it 👍
from sd-webui-lora-block-weight.
slashedstar
commented on August 20, 2024
Yeah, its fixed after updating, thanks
from sd-webui-lora-block-weight.
Related Issues (20)
- Support for OFT (and problem with bundle format) HOT 3
- Doesn't work with a1111-sd-webui-lycoris HOT 3
- Dosen't work with custom setting
- Dosen't work with custom values HOT 2
- AttributeError: 'Network' object has no attribute 'bundle_embeddings' HOT 2
- error after update new version HOT 1
- Doesn't seem to work with ADetailer HOT 2
- Can't use on stable-diffusion-webui a1111 1.7.0? HOT 3
- A Minor Issue with the Combined Use of Lora-Block-Weight and Multidiffusion-Upscaler-for-Automatic1111 HOT 1
- UnicodeDecodeError: 'utf-8' codec can't decode byte 0xa4 in position 1: invalid start byte
- LBW Issue on A1111 v1.4.0 and Lower HOT 1
- lbw= HOT 1
- AttributeError: 'ImageDraw' object has no attribute 'multiline_textsize'. Did you mean: 'multiline_text'? HOT 3
- UnboundLocalError: local variable 'currentblock' referenced before assignment HOT 3
- Enabling this on forge now causes over-fitted like results HOT 1
- Multiple loras not working properly on forge when running a batch and using start and stop HOT 1
- 同一LORAにstepstop構文をつけるとエラーが起こる HOT 4
- Huge VRAM usage with start/stop HOT 3
- Why are the results different in lbw=? HOT 4
- What is the difference between BASE and text encoder value? They generate different images. HOT 3
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from sd-webui-lora-block-weight.